gitlab-mr
Skill1 starsChanged 12 days agoMITView on GitHub
Phase 7. Commits, rebases, pushes the branch and opens the merge request (a pull request on GitHub), then links it on the ticket. Use after self-review is done and run-checks prints ALL PASS.
- Reads credentials
- Commits and pushes
4 other projects use a version of this.
Adopted by
Most recently taken up by
- bambam955/skillstheir own version, first seen Oct 30, 2026
- CedricSanchezGithub/claude-skillstheir own version, first seen Sep 21, 2026
- DeanThompson/agent-skillstheir own version, first seen May 9, 2026
- addxai/enterprise-harness-engineeringtheir own version, first seen Apr 17, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- addxai/enterprise-harness-engineering★ 44same name
- bambam955/skills★ 1same name
- DeanThompson/agent-skills★ 1same name
- CedricSanchezGithub/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/00-ticket-workflow.mdcCursor rule
- .cursor/rules/10-general-standards.mdcCursor rule
- .cursor/rules/20-backend-standards.mdcCursor rule
- .cursor/rules/30-frontend-standards.mdcCursor rule
- .cursor/rules/40-database-standards.mdcCursor rule
- .cursor/rules/50-testing-standards.mdcCursor rule
- backend-implementSkill
- chatSkill
- codebase-exploreSkill
- db-migrationSkill
- frontend-implementSkill
- implementation-planSkill
- jira-createSkill
- mr-feedbackSkill
- mr-reviewSkill
- quick-fixSkill
- run-checksSkill
- self-reviewSkill
- ticket-intakeSkill
- ticket-qaSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 1 is distinctive, and 8 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Run /run-checks now. Continue only on ALL PASS.
- Very specific: line 9
Check what will be committed: git status --short.
- Very specific: line 10
Must NOT appear: .agent/work/, .env files, build output, files not in PLAN.md.
- Very specific: line 12
Commit, one commit per logical part (e.g.
- Very specific: line 15
Update with main: git fetch origin && git rebase origin/main.
- Distinctive: line 17
After a rebase, run /run-checks again (2 Alembic heads → /db-migration step 7).
- Very specific: line 24
Create the MR (GitLab or GitHub.
- Very specific: line 26
Add --draft at the end if "Human actions required" is not None.
- Very specific: line 27
Verify: it prints a URL ending in /merge_requests/<IID> or /pull/<IID>.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Open the MR (phase 7)
Steps
- Run /run-checks now. Continue only on
ALL PASS. - Check what will be committed:
git status --short. Must NOT appear:.agent/work/,.envfiles, build output, files not in PLAN.md. - Stage files explicitly:
git add <file> <file> ...(nevergit add -Aorgit add .). - Commit, one commit per logical part (e.g. migration, backend, frontend, tests):
git commit -m "<KEY>: <type>(<scope>): <imperative summary, ≤ 72 chars>"<type>= feat | fix | refactor | test | chore. Example:PROJ-123: feat(orders): add cancel endpoint - Update with main:
git fetch origin && git rebase origin/main. Conflict in a file you did not change, or you're unsure →git rebase --abortand ask the human. After a rebase, run /run-checks again (2 Alembic heads → /db-migration step 7). - Push:
git push -u origin HEAD. Never--force. If a push is rejected, ask the human. - Proof:
bash .cursor/skills/run-checks/scripts/proof_pack.sh > .agent/work/<KEY>/proof.md. It refuses if anything changed after the lastALL PASS(an edit, a commit, a rebase): run /run-checks, commit any fix, push, and run it again. Never write or edit the proof by hand. - Fill
mr-template.md(next to this file) into.agent/work/<KEY>/MR.md. Every section, orNone. The Proof section isproof.md, pasted unedited. - Create the MR (GitLab or GitHub;
mr.shpicks the host):bash .cursor/skills/mr-feedback/scripts/mr.sh create "<KEY>: <summary>" .agent/work/<KEY>/MR.mdAdd--draftat the end if "Human actions required" is notNone. Verify: it prints a URL ending in/merge_requests/<IID>or/pull/<IID>. The IID is that number. - Save MR URL and IID in PROGRESS.md. Set
Phase: 7-mr (open). PROGRESS.md hasParent: <KEY>? Also set this sub-task's row in that parent's Roadmap (its PLAN.md) toMR !<IID>. - Post a comment (tracker MCP) on the ticket, and on its parent if it has one:
Agent: MR ready for review: <url>. ACHAT-<n>key has no ticket: skip this. - Tell the human:
MR created: <url>. After review or a pipeline result, start a new chat and type: Continue <KEY>.
Done when
- Only planned files committed, commit messages follow the format
- Branch pushed without force, MR created against
main - The MR's Proof section is
proof_pack.shoutput for the pushed head, unedited - MR URL in PROGRESS.md and on the ticket
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

